Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM65033
Volume:
10 |
6 |
Jun 2026
Pages:
1-8
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Master Of Computer Application
University B D T College of Engineering Davangere
Master Of Computer Application
University B D T College of Engineering Davangere
Crime has become a major concern in modern society due to the increasing number of criminal activities occurring in urban and rural areas. Traditional crime analysis methods based on manual record keeping and statistical observation are often slow, complex, and inefficient in identifying crime patterns and predicting future incidents. This paper presents a machine learning-based Crime Data Analysis Dashboard designed to analyze crime records efficiently and provide meaningful insights for law enforcement agencies. The proposed system uses machine learning algorithms such as Logistic Regression, Random Forest, and Decision Tree Classifier to classify and predict crime categories based on historical crime data. Data preprocessing techniques including data cleaning, feature encoding, normalization, and handling missing values are applied to improve model performance. The dashboard provides interactive visualizations such as crime distribution charts, hotspot analysis, yearly crime trends, and prediction reports for better understanding of criminal activities. The models are evaluated using Accuracy, Precision, Recall, F1-Score, and ROC-AUC metrics to measure prediction effectiveness. Experimental results show that ensemble learning models, especially Random Forest, achieve better prediction accuracy and crime classification performance compared to traditional analytical methods. The developed system can assist police departments and government authorities in monitoring crime trends, identifying high-risk areas, and improving decision-making through intelligent and real-time crime analysis.
KEYWORDS
A computer program was built here to study past crime records. It uses smart methods to guess how much crime might happen in different parts of a city. One part looks at old numbers, another checks spots where police work. Every corner of the city's safety needs gets weighed. With these facts, guesses come alive - what happened last year, which neighborhood, what kind of incident. From that, pictures form: how busy courts could get, when trouble rises, who might need help first. When models run, they hit high marks - precision, recall, F1 - all topping out near 99.7 percent when guessing where, when, or who might be involved in crime. Outcomes show city zones light up more often, summer months spike, certain neighborhoods repeat. These visuals help teams spot risky spots before trouble grows. With solid data guiding moves, police shift focus smarter, routes adjust, presence tightens where it counts most.
Aggarwal, C. C. (2015). Data Mining: The Textbook. Springer Publications. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., et al. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12, 2825–2830. McKinney, W. (2010). Data Structures for Statistical Computing in Python. Proceedings of the 9th Python in Science Conference. Van Der Walt, S., Colbert, S. C., & Varoquaux, G. (2011). The NumPy Array: A Structure for Efficient Numerical Computation. Computing in Science & Engineering, 13(2), 22– 30. Friedman, J. H. (2001). Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics, 29(5), 1189–1232. Breiman, L. (2001). Random Forests. Machine Learning Journal, 45(1), 5–32.
Publication Date
6/17/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...